MobileUse: A GUI Agent with Hierarchical Reflection for Autonomous Mobile Operation

TL;DR

MobileUse is a hierarchical reflection-based GUI agent that enhances autonomous mobile task execution by self-monitoring, error recovery, and proactive exploration, achieving state-of-the-art success rates on benchmark datasets.

Contribution

The paper introduces MobileUse, a novel GUI agent with hierarchical reflection and proactive exploration modules for improved robustness and adaptability in mobile task automation.

Findings

Achieves success rates of 62.9% on AndroidWorld and 44.2% on AndroidLab.

Demonstrates state-of-the-art performance in mobile task execution.

Provides an open-source toolkit for real-world mobile automation.

Abstract

Recent advances in Multimodal Large Language Models (MLLMs) have enabled the development of mobile agents that can understand visual inputs and follow user instructions, unlocking new possibilities for automating complex tasks on mobile devices. However, applying these models to real-world mobile scenarios remains a significant challenge due to the long-horizon task execution, difficulty in error recovery, and the cold-start problem in unfamiliar environments. To address these challenges, we propose MobileUse, a GUI agent designed for robust and adaptive mobile task execution. To improve resilience in long-horizon tasks and dynamic environments, we introduce a hierarchical reflection architecture that enables the agent to self-monitor, detect, and recover from errors across multiple temporal scales-ranging from individual actions to overall task completion-while maintaining efficiency through a reflection-on-demand strategy. To tackle cold-start issues, we further introduce a proactive exploration module, which enriches the agent's understanding of the environment through self-planned exploration. Evaluations on AndroidWorld and AndroidLab benchmarks demonstrate that MobileUse establishes new state-of-the-art performance, achieving success rates of 62.9% and 44.2%, respectively. To facilitate real-world applications, we release an out-of-the-box toolkit for automated task execution on physical mobile devices, which is available at https://github.com/MadeAgents/mobile-use.